© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94862
    Prev
    Next
    INDEX
    Explanations

    actions, behavior, relationships, processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.28
     myſelf
    -1.27
     leaſt
    -1.20
     purpoſe
    -1.19
     houſe
    -1.17
     himſelf
    -1.16
     whoſe
    -1.10
     pleaſure
    -1.10
     Jefus
    -1.09
     ſever
    -1.09
    POSITIVE LOGITS
     To
    0.96
     For
    0.94
     In
    0.93
     As
    0.88
     
    0.86
     And
    0.85
     "
    0.82
     A
    0.81
     “
    0.81
     With
    0.79
    Activations Density 0.563%

    No Known Activations